# Context.dev — how to use (mcp.ai)

Connect your Context.dev account and use 11 tools for developer tools straight from your AI agent. Connect with your own API key. Context.dev provides web scraping, extraction, brand intelligence, monitoring, and structured web data APIs for AI applications.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_context_dev?ms=1787291400000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `context_dev_extract_structured_web_data`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/context_dev`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/context_dev/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/context_dev/extract/structured/web/data` — Crawl relevant pages from a website and return data matching a caller-provided JSON Schema and extraction instructions. This is a higher-cost metered call; use SCRAPE_WEBPAGE_MARKDOWN when Markdown is
  - body: { url: string, tags?: string[], max_depth?: integer, max_pages?: integer, fact_check?: boolean, instructions?: string, output_schema: object, stop_after_ms?: integer, follow_subdomains?: boolean }
- `POST https://api.mcp.ai/api/context_dev/get/brand` — Retrieve enriched brand identity, logos, colors, industry, and description using exactly one domain, name, work email, ticker, direct URL, or transaction descriptor. Use SEARCH_BRANDS for inexpensive 
  - body: { city?: string, tags?: string[], phone?: string|integer|number, country?: string, max_speed?: boolean, identifier: string, max_age_ms?: integer, timeout_ms?: integer, lookup_type: string, force_language?: string, ticker_exchange?: string, high_confidence_only?: boolean, merchant_category_code?: string|integer|number }
- `POST https://api.mcp.ai/api/context_dev/get/monitor/limits` — Return the connected account's plan and current monitor usage versus its monitor limit.
- `POST https://api.mcp.ai/api/context_dev/get/webdb/usage` — Return WebDB credit balance, period consumption, row count, storage, and per-collection usage for an optional time range.
  - body: { tags?: string[], to_time?: string, from_time?: string }
- `POST https://api.mcp.ai/api/context_dev/get/website/styleguide` — Extract a website's colors, typography, spacing, shadows, font assets, and common component styles from either a domain or one direct URL. A successful extraction normally consumes 10 Context.dev cred
  - body: { tags?: string[], domain?: string, direct_url?: string, max_age_ms?: integer, timeout_ms?: integer, color_scheme?: string }
- `POST https://api.mcp.ai/api/context_dev/list/batches` — List and filter the connected account's asynchronous web batches from newest to oldest, returning one cursor-controlled page.
  - body: { tags?: string[], limit?: integer, query?: string, cursor?: string, status?: string, search_type?: string }
- `POST https://api.mcp.ai/api/context_dev/list/monitors` — List and filter the connected organization's web monitors, returning one cursor-controlled page.
  - body: { tags?: string[], limit?: integer, query?: string, cursor?: string, status?: string, search_type?: string, target_type?: string, search_fields?: string[], change_detection_type?: string }
- `POST https://api.mcp.ai/api/context_dev/list/webdb/collections` — List the connected account's WebDB collections and return one cursor-controlled page, including each collection's sources, extraction configuration, status, usage, and timestamps.
  - body: { tags?: string[], limit?: integer, cursor?: string }
- `POST https://api.mcp.ai/api/context_dev/parse/file` — Convert an uploaded document, image, source file, or data file into LLM-usable Markdown.
  - body: { ocr?: boolean, file: object, tags?: string[], pdf_end?: integer, extension?: string, pdf_start?: integer, include_links?: boolean, include_images?: boolean, zero_data_retention?: boolean, use_main_content_only?: boolean }
- `POST https://api.mcp.ai/api/context_dev/scrape/webpage/markdown` — Render one public URL and return its main or CSS-selected content as Markdown. This free-tier tool does not perform paid browser actions. A successful scrape normally consumes one Context.dev credit.
  - body: { url: string, tags?: string[], country?: string, max_age_ms?: integer, timeout_ms?: integer, wait_for_ms?: integer, include_links?: boolean, include_frames?: boolean, include_images?: boolean, exclude_selectors?: string[], include_selectors?: string[], settle_animations?: boolean, zero_data_retention?: boolean, use_main_content_only?: boolean }
- `POST https://api.mcp.ai/api/context_dev/search/brands` — Prefix-search Context.dev's existing brand index by company name or domain and return up to 10 lightweight matches.
  - body: { tags?: string[], query: string }

## Example prompts
- "What can I do in Context.dev?"
- "Show me a summary of my Context.dev account"

## More
- Page: https://mcp.ai/context_dev
- Agent spec (llms.txt): https://mcp.ai/context_dev/llms.txt
- Postman collection: https://mcp.ai/context_dev/postman.json